This paper surveys applications of data mining techniques to large text col
lections, and illustrates how those techniques can be used to support the m
anagement of science and technology research. Specific issues that arise re
peatedly in the conduct of research management are described, and a textual
data mining architecture that extends a classic paradigm for knowledge dis
covery in databases is introduced. That architecture integrates information
retrieval from text collections, information extraction to obtain data fro
m individual texts, data warehousing for the extracted data, data mining to
discover useful patterns in the data, and visualization of the resulting p
atterns. At the core of this architecture is a broad view of data mining-th
e process of discovering patterns in large collections of data-and that ste
p is described in some detail. The final section of the paper illustrates h
ow these ideas can be applied in practice, drawing upon examples from the r
ecently completed first phase of the textual data mining program at the Off
ice of Naval Research. The paper concludes by identifying some research dir
ections that offer significant potential for improving the utility of textu
al data mining for research management applications.